Support processing multiple bibliography files (jaspervdj#898)

* Support processing multiple bibliography files Pandoc Citeproc supports taking multiple bibliography files as input by passing a MetaList to the "bibliography" key instead of a single string. This keeps the original processPandocBiblio function taking a single bibliography, and adds a processPandocBiblios taking a list; the original function now just calls the new one. * Add tests for readPandocBiblios
Zekt · Oct 25, 2021 · f7f2cdd · f7f2cdd
1 parent b8df202
commit f7f2cdd
Show file tree

Hide file tree

Showing 6 changed files with 120 additions and 15 deletions.
diff --git a/hakyll.cabal b/hakyll.cabal
@@ -61,10 +61,13 @@ Extra-source-files:
   CHANGELOG.md
   tests/data/biblio/chicago.csl
   tests/data/biblio/cites-meijer.golden
+  tests/data/biblio/cites-multiple.golden
+  tests/data/biblio/cites-multiple.markdown
   tests/data/biblio/default.html
   tests/data/biblio/page.markdown
   tests/data/biblio/refs.bib
   tests/data/biblio/refs.yaml
+  tests/data/biblio/refs2.yaml
   tests/data/embed.html
   tests/data/example.md
   tests/data/example.md.metadata

diff --git a/lib/Hakyll/Web/Pandoc/Biblio.hs b/lib/Hakyll/Web/Pandoc/Biblio.hs
@@ -21,7 +21,9 @@ module Hakyll.Web.Pandoc.Biblio
     , Biblio (..)
     , biblioCompiler
     , readPandocBiblio
+    , readPandocBiblios
     , processPandocBiblio
+    , processPandocBiblios
     , pandocBiblioCompiler
     ) where
 
@@ -46,7 +48,7 @@ import           Text.Pandoc                   (Extension (..), Pandoc,
                                                 enableExtension)
 import qualified Text.Pandoc                   as Pandoc
 import qualified Text.Pandoc.Citeproc          as Pandoc (processCitations)
-import           System.FilePath               (takeExtension)
+import           System.FilePath               (addExtension, takeExtension)
 
 
 --------------------------------------------------------------------------------
@@ -88,17 +90,30 @@ readPandocBiblio :: ReaderOptions
                  -> Item Biblio
                  -> (Item String)
                  -> Compiler (Item Pandoc)
-readPandocBiblio ropt csl biblio item = do
+readPandocBiblio ropt csl biblio = readPandocBiblios ropt csl [biblio]
+
+readPandocBiblios :: ReaderOptions
+                  -> Item CSL
+                  -> [Item Biblio]
+                  -> (Item String)
+                  -> Compiler (Item Pandoc)
+readPandocBiblios ropt csl biblios item = do
   pandoc <- readPandocWith ropt item
-  processPandocBiblio csl biblio pandoc
+  processPandocBiblios csl biblios pandoc
 
 
 --------------------------------------------------------------------------------
 processPandocBiblio :: Item CSL
                     -> Item Biblio
                     -> (Item Pandoc)
                     -> Compiler (Item Pandoc)
-processPandocBiblio csl biblio item = do
+processPandocBiblio csl biblio = processPandocBiblios csl [biblio]
+
+processPandocBiblios :: Item CSL
+                     -> [Item Biblio]
+                     -> (Item Pandoc)
+                     -> Compiler (Item Pandoc)
+processPandocBiblios csl biblios item = do
     -- It's not straightforward to use the Pandoc API as of 2.11 to deal with
     -- citations, since it doesn't export many things in 'Text.Pandoc.Citeproc'.
     -- The 'citeproc' package is also hard to use.
@@ -110,19 +125,25 @@ processPandocBiblio csl biblio item = do
     -- ersatz filesystem.
     let Pandoc.Pandoc (Pandoc.Meta meta) blocks = itemBody item
         cslFile = Pandoc.FileInfo zeroTime . unCSL $ itemBody csl
-        bibFile = Pandoc.FileInfo zeroTime . unBiblio $ itemBody biblio
-        bibFileType = takeExtension $ toFilePath $ itemIdentifier biblio
-        internalBibFileName = "_hakyll/refs." ++ bibFileType
-
-        addBiblioFiles = \st -> st
-            { Pandoc.stFiles =
-                Pandoc.insertInFileTree "_hakyll/style.csl" cslFile .
-                Pandoc.insertInFileTree internalBibFileName bibFile $
-                Pandoc.stFiles st
-            }
+        bibFiles = zipWith (\x y ->
+            ( addExtension ("_hakyll/bibliography-" ++ show x)
+                           (takeExtension $ toFilePath $ itemIdentifier y)
+            , Pandoc.FileInfo zeroTime . unBiblio . itemBody $ y
+            )
+          )
+          [0 ..]
+          biblios
+
+        stFiles = foldr ((.) . uncurry Pandoc.insertInFileTree)
+                    (Pandoc.insertInFileTree "_hakyll/style.csl" cslFile)
+                    bibFiles
+
+        addBiblioFiles = \st -> st { Pandoc.stFiles = stFiles $ Pandoc.stFiles st }
+
         biblioMeta = Pandoc.Meta .
             Map.insert "csl" (Pandoc.MetaString "_hakyll/style.csl") .
-            Map.insert "bibliography" (Pandoc.MetaString $ T.pack internalBibFileName) $
+            Map.insert "bibliography"
+              (Pandoc.MetaList $ map (Pandoc.MetaString . T.pack . fst) bibFiles) $
             meta
         errOrPandoc = Pandoc.runPure $ do
             Pandoc.modifyPureState addBiblioFiles

diff --git a/tests/Hakyll/Web/Pandoc/Biblio/Tests.hs b/tests/Hakyll/Web/Pandoc/Biblio/Tests.hs
@@ -26,6 +26,7 @@ tests :: TestTree
 tests = testGroup "Hakyll.Web.Pandoc.Biblio.Tests" $
     [ goldenTest01
     , goldenTest02
+    , goldenTest03
     ]
 
 --------------------------------------------------------------------------------
@@ -98,3 +99,38 @@ goldenTest02 =
             cleanTestEnv
 
             return output)
+
+goldenTest03 :: TestTree
+goldenTest03 =
+    goldenVsString
+        "biblio03"
+        (goldenTestsDataDir </> "cites-multiple.golden")
+        (do
+            -- Code lifted from https://github.com/jaspervdj/hakyll-citeproc-example.
+            logger <- Logger.new Logger.Error
+            let config = testConfiguration { providerDirectory = goldenTestsDataDir }
+            _ <- run RunModeNormal config logger $ do
+                let myPandocBiblioCompiler = do
+                        csl <- load "chicago.csl"
+                        bib1 <- load "refs.bib"
+                        bib2 <- load "refs2.yaml"
+                        getResourceBody >>=
+                            readPandocBiblios defaultHakyllReaderOptions csl [bib1, bib2] >>=
+                            return . writePandoc
+
+                match "default.html" $ compile templateCompiler
+                match "chicago.csl" $ compile cslCompiler
+                match "refs.bib"    $ compile biblioCompiler
+                match "refs2.yaml"    $ compile biblioCompiler
+                match "cites-multiple.markdown" $ do
+                    route $ setExtension "html"
+                    compile $
+                        myPandocBiblioCompiler >>=
+                        loadAndApplyTemplate "default.html" defaultContext
+
+            output <- fmap LBS.fromStrict $ B.readFile $
+                    destinationDirectory testConfiguration </> "cites-multiple.html"
+
+            cleanTestEnv
+
+            return output)
diff --git a/tests/data/biblio/cites-multiple.golden b/tests/data/biblio/cites-multiple.golden
@@ -0,0 +1,20 @@
+<!doctype html>
+<html lang="en">
+    <head>
+        <meta charset="utf-8">
+        <title>This page cites a paper and a book.</title>
+    </head>
+    <body>
+        <h1>This page cites a paper and a book.</h1>
+        <p>I would like to cite one of my favourite papers <span class="citation" data-cites="meijer1991functional">(Meijer, Fokkinga, and Paterson 1991)</span> here.</p>
+<p>And also a book <span class="citation" data-cites="lipovaca2012">(Lipovača 2012)</span>.</p>
+<div id="refs" class="references csl-bib-body hanging-indent" role="doc-bibliography">
+<div id="ref-lipovaca2012" class="csl-entry" role="doc-biblioentry">
+Lipovača, Miran. 2012. <em>Learn You a Haskell for Great Good! A Beginner’s Guide</em>. San Francisco, CA: No Starch Press.
+</div>
+<div id="ref-meijer1991functional" class="csl-entry" role="doc-biblioentry">
+Meijer, Erik, Maarten Fokkinga, and Ross Paterson. 1991. <span>“Functional Programming with Bananas, Lenses, Envelopes and Barbed Wire.”</span> In <em>Conference on Functional Programming Languages and Computer Architecture</em>, 124–44. Springer.
+</div>
+</div>
+    </body>
+</html>
diff --git a/tests/data/biblio/cites-multiple.markdown b/tests/data/biblio/cites-multiple.markdown
@@ -0,0 +1,7 @@
+---
+title: This page cites a paper and a book.
+---
+
+I would like to cite one of my favourite papers [@meijer1991functional] here.
+
+And also a book [@lipovaca2012].
diff --git a/tests/data/biblio/refs2.yaml b/tests/data/biblio/refs2.yaml
@@ -0,0 +1,18 @@
+---
+references:
+- id: lipovaca2012
+  author:
+    - family: Lipovača
+      given: Miran
+  call-number: QA76.73.H37 L69 2012
+  event-place: San Francisco, CA
+  ISBN: 978-1-59327-283-8
+  issued:
+    - year: 2012
+  number-of-pages: '375'
+  publisher: No Starch Press
+  publisher-place: San Francisco, CA
+  source: Library of Congress ISBN
+  title: Learn you a Haskell for great good! a beginner's guide
+  type: book
+...